MedHallTune: An Instruction-Tuning Benchmark for Mitigating Medical Hallucination in Vision-Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915176614199296 |
|---|---|
| author | Yan, Qiao Yuan, Yuchen Hu, Xiaowei Wang, Yihan Xu, Jiaqi Li, Jinpeng Fu, Chi-Wing Heng, Pheng-Ann |
| author_facet | Yan, Qiao Yuan, Yuchen Hu, Xiaowei Wang, Yihan Xu, Jiaqi Li, Jinpeng Fu, Chi-Wing Heng, Pheng-Ann |
| contents | The increasing use of vision-language models (VLMs) in healthcare applications presents great challenges related to hallucinations, in which the models may generate seemingly plausible results that are in fact incorrect. Such hallucinations can jeopardize clinical decision making, potentially harming the diagnosis and treatments. In this work, we propose MedHallTune, a large-scale benchmark designed specifically to evaluate and mitigate hallucinations in medical VLMs. Comprising over 100,000 images and 1,000,000 instruction pairs, MedHallTune includes both hallucination and non-hallucination samples, each with ground-truth annotations. We conduct a comprehensive evaluation of current medical and general VLMs using MedHallTune, assessing their performance across key metrics, including clinical accuracy, relevance, detail level, and risk level. The experimental results show that fine-tuning with MedHallTune successfully improves the ability of several existing models to manage hallucinations and boost their zero-shot performance on downstream visual-question-answering (VQA) tasks, making them more reliable for practical medical applications. Our work contributes to the development of more trustworthy VLMs. Codes and dataset will be available at \href{https://github.com/russellyq/MedHallTune}{MedHallTune}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_20780 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MedHallTune: An Instruction-Tuning Benchmark for Mitigating Medical Hallucination in Vision-Language Models Yan, Qiao Yuan, Yuchen Hu, Xiaowei Wang, Yihan Xu, Jiaqi Li, Jinpeng Fu, Chi-Wing Heng, Pheng-Ann Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition The increasing use of vision-language models (VLMs) in healthcare applications presents great challenges related to hallucinations, in which the models may generate seemingly plausible results that are in fact incorrect. Such hallucinations can jeopardize clinical decision making, potentially harming the diagnosis and treatments. In this work, we propose MedHallTune, a large-scale benchmark designed specifically to evaluate and mitigate hallucinations in medical VLMs. Comprising over 100,000 images and 1,000,000 instruction pairs, MedHallTune includes both hallucination and non-hallucination samples, each with ground-truth annotations. We conduct a comprehensive evaluation of current medical and general VLMs using MedHallTune, assessing their performance across key metrics, including clinical accuracy, relevance, detail level, and risk level. The experimental results show that fine-tuning with MedHallTune successfully improves the ability of several existing models to manage hallucinations and boost their zero-shot performance on downstream visual-question-answering (VQA) tasks, making them more reliable for practical medical applications. Our work contributes to the development of more trustworthy VLMs. Codes and dataset will be available at \href{https://github.com/russellyq/MedHallTune}{MedHallTune}. |
| title | MedHallTune: An Instruction-Tuning Benchmark for Mitigating Medical Hallucination in Vision-Language Models |
| topic | Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.20780 |